Image Classification Using MobileNetV2¶
Image Classification using Neural Networks
This notebook guides you through the process of image classification using the MobileNetV2 model from TensorFlow. The assignment is based on the tutorials provided in Module 12.
Objectives
- Understand the basics of image classification.
- Learn how to implement MobileNetV2 for image classification.
- Classify a given image and interpret the results.
Matthew Acs
Setup¶
This section is sets up the notebook by ensuring all necessary libraries and dependencies are installed and imported, creating an environment for image classification tasks. The setup involves installing key libraries such as TensorFlow, which is fundamental for loading and operating the MobileNetV2 model, Numpy for efficient data handling and preprocessing, and Matplotlib for visualizing images.
Install Required Libraries¶
The initial block of code utilizes IPython's capabilities to suppress verbose output while installing these libraries via pip, ensuring a clean and readable notebook setup.
from IPython.utils.io import capture_output
with capture_output() as captured:
%pip install tensorflow tensorflow_hub numpy matplotlib
Import Libraries¶
Following installations, the subsequent code block imports these libraries along with others such as PIL for image manipulation and additional TensorFlow components crucial for image preprocessing and decoding model predictions.
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
import requests
from PIL import Image
from io import BytesIO
from tensorflow.keras.preprocessing.image import img_to_array, load_img
from tensorflow.keras.applications import MobileNetV2
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input, decode_predictions
This setup is necessary for the execution of subsequent tasks in the notebook.
Load the Pre-trained Model¶
In this section, we start by loading the pre-trained MobileNetV2 model from TensorFlow's model library. MobileNetV2 is highly effective in image classification tasks and comes equipped with weights trained on the ImageNet dataset. The code shown instantiates the MobileNetV2 model with these ImageNet weights, preparing it to classify images across a broad range of categories. The output indicates the successful download of the necessary model weights, ensuring that the model is ready to be used for making predictions. The model is the foundational tool for the image classification task.
Shown below is the model's architecture.
# Load the pre-trained MobileNetV2 model
model = MobileNetV2(weights='imagenet')
model.summary()
Model: "mobilenetv2_1.00_224"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_4 (InputLayer) [(None, 224, 224, 3)] 0 []
Conv1 (Conv2D) (None, 112, 112, 32) 864 ['input_4[0][0]']
bn_Conv1 (BatchNormalizati (None, 112, 112, 32) 128 ['Conv1[0][0]']
on)
Conv1_relu (ReLU) (None, 112, 112, 32) 0 ['bn_Conv1[0][0]']
expanded_conv_depthwise (D (None, 112, 112, 32) 288 ['Conv1_relu[0][0]']
epthwiseConv2D)
expanded_conv_depthwise_BN (None, 112, 112, 32) 128 ['expanded_conv_depthwise[0][0
(BatchNormalization) ]']
expanded_conv_depthwise_re (None, 112, 112, 32) 0 ['expanded_conv_depthwise_BN[0
lu (ReLU) ][0]']
expanded_conv_project (Con (None, 112, 112, 16) 512 ['expanded_conv_depthwise_relu
v2D) [0][0]']
expanded_conv_project_BN ( (None, 112, 112, 16) 64 ['expanded_conv_project[0][0]'
BatchNormalization) ]
block_1_expand (Conv2D) (None, 112, 112, 96) 1536 ['expanded_conv_project_BN[0][
0]']
block_1_expand_BN (BatchNo (None, 112, 112, 96) 384 ['block_1_expand[0][0]']
rmalization)
block_1_expand_relu (ReLU) (None, 112, 112, 96) 0 ['block_1_expand_BN[0][0]']
block_1_pad (ZeroPadding2D (None, 113, 113, 96) 0 ['block_1_expand_relu[0][0]']
)
block_1_depthwise (Depthwi (None, 56, 56, 96) 864 ['block_1_pad[0][0]']
seConv2D)
block_1_depthwise_BN (Batc (None, 56, 56, 96) 384 ['block_1_depthwise[0][0]']
hNormalization)
block_1_depthwise_relu (Re (None, 56, 56, 96) 0 ['block_1_depthwise_BN[0][0]']
LU)
block_1_project (Conv2D) (None, 56, 56, 24) 2304 ['block_1_depthwise_relu[0][0]
']
block_1_project_BN (BatchN (None, 56, 56, 24) 96 ['block_1_project[0][0]']
ormalization)
block_2_expand (Conv2D) (None, 56, 56, 144) 3456 ['block_1_project_BN[0][0]']
block_2_expand_BN (BatchNo (None, 56, 56, 144) 576 ['block_2_expand[0][0]']
rmalization)
block_2_expand_relu (ReLU) (None, 56, 56, 144) 0 ['block_2_expand_BN[0][0]']
block_2_depthwise (Depthwi (None, 56, 56, 144) 1296 ['block_2_expand_relu[0][0]']
seConv2D)
block_2_depthwise_BN (Batc (None, 56, 56, 144) 576 ['block_2_depthwise[0][0]']
hNormalization)
block_2_depthwise_relu (Re (None, 56, 56, 144) 0 ['block_2_depthwise_BN[0][0]']
LU)
block_2_project (Conv2D) (None, 56, 56, 24) 3456 ['block_2_depthwise_relu[0][0]
']
block_2_project_BN (BatchN (None, 56, 56, 24) 96 ['block_2_project[0][0]']
ormalization)
block_2_add (Add) (None, 56, 56, 24) 0 ['block_1_project_BN[0][0]',
'block_2_project_BN[0][0]']
block_3_expand (Conv2D) (None, 56, 56, 144) 3456 ['block_2_add[0][0]']
block_3_expand_BN (BatchNo (None, 56, 56, 144) 576 ['block_3_expand[0][0]']
rmalization)
block_3_expand_relu (ReLU) (None, 56, 56, 144) 0 ['block_3_expand_BN[0][0]']
block_3_pad (ZeroPadding2D (None, 57, 57, 144) 0 ['block_3_expand_relu[0][0]']
)
block_3_depthwise (Depthwi (None, 28, 28, 144) 1296 ['block_3_pad[0][0]']
seConv2D)
block_3_depthwise_BN (Batc (None, 28, 28, 144) 576 ['block_3_depthwise[0][0]']
hNormalization)
block_3_depthwise_relu (Re (None, 28, 28, 144) 0 ['block_3_depthwise_BN[0][0]']
LU)
block_3_project (Conv2D) (None, 28, 28, 32) 4608 ['block_3_depthwise_relu[0][0]
']
block_3_project_BN (BatchN (None, 28, 28, 32) 128 ['block_3_project[0][0]']
ormalization)
block_4_expand (Conv2D) (None, 28, 28, 192) 6144 ['block_3_project_BN[0][0]']
block_4_expand_BN (BatchNo (None, 28, 28, 192) 768 ['block_4_expand[0][0]']
rmalization)
block_4_expand_relu (ReLU) (None, 28, 28, 192) 0 ['block_4_expand_BN[0][0]']
block_4_depthwise (Depthwi (None, 28, 28, 192) 1728 ['block_4_expand_relu[0][0]']
seConv2D)
block_4_depthwise_BN (Batc (None, 28, 28, 192) 768 ['block_4_depthwise[0][0]']
hNormalization)
block_4_depthwise_relu (Re (None, 28, 28, 192) 0 ['block_4_depthwise_BN[0][0]']
LU)
block_4_project (Conv2D) (None, 28, 28, 32) 6144 ['block_4_depthwise_relu[0][0]
']
block_4_project_BN (BatchN (None, 28, 28, 32) 128 ['block_4_project[0][0]']
ormalization)
block_4_add (Add) (None, 28, 28, 32) 0 ['block_3_project_BN[0][0]',
'block_4_project_BN[0][0]']
block_5_expand (Conv2D) (None, 28, 28, 192) 6144 ['block_4_add[0][0]']
block_5_expand_BN (BatchNo (None, 28, 28, 192) 768 ['block_5_expand[0][0]']
rmalization)
block_5_expand_relu (ReLU) (None, 28, 28, 192) 0 ['block_5_expand_BN[0][0]']
block_5_depthwise (Depthwi (None, 28, 28, 192) 1728 ['block_5_expand_relu[0][0]']
seConv2D)
block_5_depthwise_BN (Batc (None, 28, 28, 192) 768 ['block_5_depthwise[0][0]']
hNormalization)
block_5_depthwise_relu (Re (None, 28, 28, 192) 0 ['block_5_depthwise_BN[0][0]']
LU)
block_5_project (Conv2D) (None, 28, 28, 32) 6144 ['block_5_depthwise_relu[0][0]
']
block_5_project_BN (BatchN (None, 28, 28, 32) 128 ['block_5_project[0][0]']
ormalization)
block_5_add (Add) (None, 28, 28, 32) 0 ['block_4_add[0][0]',
'block_5_project_BN[0][0]']
block_6_expand (Conv2D) (None, 28, 28, 192) 6144 ['block_5_add[0][0]']
block_6_expand_BN (BatchNo (None, 28, 28, 192) 768 ['block_6_expand[0][0]']
rmalization)
block_6_expand_relu (ReLU) (None, 28, 28, 192) 0 ['block_6_expand_BN[0][0]']
block_6_pad (ZeroPadding2D (None, 29, 29, 192) 0 ['block_6_expand_relu[0][0]']
)
block_6_depthwise (Depthwi (None, 14, 14, 192) 1728 ['block_6_pad[0][0]']
seConv2D)
block_6_depthwise_BN (Batc (None, 14, 14, 192) 768 ['block_6_depthwise[0][0]']
hNormalization)
block_6_depthwise_relu (Re (None, 14, 14, 192) 0 ['block_6_depthwise_BN[0][0]']
LU)
block_6_project (Conv2D) (None, 14, 14, 64) 12288 ['block_6_depthwise_relu[0][0]
']
block_6_project_BN (BatchN (None, 14, 14, 64) 256 ['block_6_project[0][0]']
ormalization)
block_7_expand (Conv2D) (None, 14, 14, 384) 24576 ['block_6_project_BN[0][0]']
block_7_expand_BN (BatchNo (None, 14, 14, 384) 1536 ['block_7_expand[0][0]']
rmalization)
block_7_expand_relu (ReLU) (None, 14, 14, 384) 0 ['block_7_expand_BN[0][0]']
block_7_depthwise (Depthwi (None, 14, 14, 384) 3456 ['block_7_expand_relu[0][0]']
seConv2D)
block_7_depthwise_BN (Batc (None, 14, 14, 384) 1536 ['block_7_depthwise[0][0]']
hNormalization)
block_7_depthwise_relu (Re (None, 14, 14, 384) 0 ['block_7_depthwise_BN[0][0]']
LU)
block_7_project (Conv2D) (None, 14, 14, 64) 24576 ['block_7_depthwise_relu[0][0]
']
block_7_project_BN (BatchN (None, 14, 14, 64) 256 ['block_7_project[0][0]']
ormalization)
block_7_add (Add) (None, 14, 14, 64) 0 ['block_6_project_BN[0][0]',
'block_7_project_BN[0][0]']
block_8_expand (Conv2D) (None, 14, 14, 384) 24576 ['block_7_add[0][0]']
block_8_expand_BN (BatchNo (None, 14, 14, 384) 1536 ['block_8_expand[0][0]']
rmalization)
block_8_expand_relu (ReLU) (None, 14, 14, 384) 0 ['block_8_expand_BN[0][0]']
block_8_depthwise (Depthwi (None, 14, 14, 384) 3456 ['block_8_expand_relu[0][0]']
seConv2D)
block_8_depthwise_BN (Batc (None, 14, 14, 384) 1536 ['block_8_depthwise[0][0]']
hNormalization)
block_8_depthwise_relu (Re (None, 14, 14, 384) 0 ['block_8_depthwise_BN[0][0]']
LU)
block_8_project (Conv2D) (None, 14, 14, 64) 24576 ['block_8_depthwise_relu[0][0]
']
block_8_project_BN (BatchN (None, 14, 14, 64) 256 ['block_8_project[0][0]']
ormalization)
block_8_add (Add) (None, 14, 14, 64) 0 ['block_7_add[0][0]',
'block_8_project_BN[0][0]']
block_9_expand (Conv2D) (None, 14, 14, 384) 24576 ['block_8_add[0][0]']
block_9_expand_BN (BatchNo (None, 14, 14, 384) 1536 ['block_9_expand[0][0]']
rmalization)
block_9_expand_relu (ReLU) (None, 14, 14, 384) 0 ['block_9_expand_BN[0][0]']
block_9_depthwise (Depthwi (None, 14, 14, 384) 3456 ['block_9_expand_relu[0][0]']
seConv2D)
block_9_depthwise_BN (Batc (None, 14, 14, 384) 1536 ['block_9_depthwise[0][0]']
hNormalization)
block_9_depthwise_relu (Re (None, 14, 14, 384) 0 ['block_9_depthwise_BN[0][0]']
LU)
block_9_project (Conv2D) (None, 14, 14, 64) 24576 ['block_9_depthwise_relu[0][0]
']
block_9_project_BN (BatchN (None, 14, 14, 64) 256 ['block_9_project[0][0]']
ormalization)
block_9_add (Add) (None, 14, 14, 64) 0 ['block_8_add[0][0]',
'block_9_project_BN[0][0]']
block_10_expand (Conv2D) (None, 14, 14, 384) 24576 ['block_9_add[0][0]']
block_10_expand_BN (BatchN (None, 14, 14, 384) 1536 ['block_10_expand[0][0]']
ormalization)
block_10_expand_relu (ReLU (None, 14, 14, 384) 0 ['block_10_expand_BN[0][0]']
)
block_10_depthwise (Depthw (None, 14, 14, 384) 3456 ['block_10_expand_relu[0][0]']
iseConv2D)
block_10_depthwise_BN (Bat (None, 14, 14, 384) 1536 ['block_10_depthwise[0][0]']
chNormalization)
block_10_depthwise_relu (R (None, 14, 14, 384) 0 ['block_10_depthwise_BN[0][0]'
eLU) ]
block_10_project (Conv2D) (None, 14, 14, 96) 36864 ['block_10_depthwise_relu[0][0
]']
block_10_project_BN (Batch (None, 14, 14, 96) 384 ['block_10_project[0][0]']
Normalization)
block_11_expand (Conv2D) (None, 14, 14, 576) 55296 ['block_10_project_BN[0][0]']
block_11_expand_BN (BatchN (None, 14, 14, 576) 2304 ['block_11_expand[0][0]']
ormalization)
block_11_expand_relu (ReLU (None, 14, 14, 576) 0 ['block_11_expand_BN[0][0]']
)
block_11_depthwise (Depthw (None, 14, 14, 576) 5184 ['block_11_expand_relu[0][0]']
iseConv2D)
block_11_depthwise_BN (Bat (None, 14, 14, 576) 2304 ['block_11_depthwise[0][0]']
chNormalization)
block_11_depthwise_relu (R (None, 14, 14, 576) 0 ['block_11_depthwise_BN[0][0]'
eLU) ]
block_11_project (Conv2D) (None, 14, 14, 96) 55296 ['block_11_depthwise_relu[0][0
]']
block_11_project_BN (Batch (None, 14, 14, 96) 384 ['block_11_project[0][0]']
Normalization)
block_11_add (Add) (None, 14, 14, 96) 0 ['block_10_project_BN[0][0]',
'block_11_project_BN[0][0]']
block_12_expand (Conv2D) (None, 14, 14, 576) 55296 ['block_11_add[0][0]']
block_12_expand_BN (BatchN (None, 14, 14, 576) 2304 ['block_12_expand[0][0]']
ormalization)
block_12_expand_relu (ReLU (None, 14, 14, 576) 0 ['block_12_expand_BN[0][0]']
)
block_12_depthwise (Depthw (None, 14, 14, 576) 5184 ['block_12_expand_relu[0][0]']
iseConv2D)
block_12_depthwise_BN (Bat (None, 14, 14, 576) 2304 ['block_12_depthwise[0][0]']
chNormalization)
block_12_depthwise_relu (R (None, 14, 14, 576) 0 ['block_12_depthwise_BN[0][0]'
eLU) ]
block_12_project (Conv2D) (None, 14, 14, 96) 55296 ['block_12_depthwise_relu[0][0
]']
block_12_project_BN (Batch (None, 14, 14, 96) 384 ['block_12_project[0][0]']
Normalization)
block_12_add (Add) (None, 14, 14, 96) 0 ['block_11_add[0][0]',
'block_12_project_BN[0][0]']
block_13_expand (Conv2D) (None, 14, 14, 576) 55296 ['block_12_add[0][0]']
block_13_expand_BN (BatchN (None, 14, 14, 576) 2304 ['block_13_expand[0][0]']
ormalization)
block_13_expand_relu (ReLU (None, 14, 14, 576) 0 ['block_13_expand_BN[0][0]']
)
block_13_pad (ZeroPadding2 (None, 15, 15, 576) 0 ['block_13_expand_relu[0][0]']
D)
block_13_depthwise (Depthw (None, 7, 7, 576) 5184 ['block_13_pad[0][0]']
iseConv2D)
block_13_depthwise_BN (Bat (None, 7, 7, 576) 2304 ['block_13_depthwise[0][0]']
chNormalization)
block_13_depthwise_relu (R (None, 7, 7, 576) 0 ['block_13_depthwise_BN[0][0]'
eLU) ]
block_13_project (Conv2D) (None, 7, 7, 160) 92160 ['block_13_depthwise_relu[0][0
]']
block_13_project_BN (Batch (None, 7, 7, 160) 640 ['block_13_project[0][0]']
Normalization)
block_14_expand (Conv2D) (None, 7, 7, 960) 153600 ['block_13_project_BN[0][0]']
block_14_expand_BN (BatchN (None, 7, 7, 960) 3840 ['block_14_expand[0][0]']
ormalization)
block_14_expand_relu (ReLU (None, 7, 7, 960) 0 ['block_14_expand_BN[0][0]']
)
block_14_depthwise (Depthw (None, 7, 7, 960) 8640 ['block_14_expand_relu[0][0]']
iseConv2D)
block_14_depthwise_BN (Bat (None, 7, 7, 960) 3840 ['block_14_depthwise[0][0]']
chNormalization)
block_14_depthwise_relu (R (None, 7, 7, 960) 0 ['block_14_depthwise_BN[0][0]'
eLU) ]
block_14_project (Conv2D) (None, 7, 7, 160) 153600 ['block_14_depthwise_relu[0][0
]']
block_14_project_BN (Batch (None, 7, 7, 160) 640 ['block_14_project[0][0]']
Normalization)
block_14_add (Add) (None, 7, 7, 160) 0 ['block_13_project_BN[0][0]',
'block_14_project_BN[0][0]']
block_15_expand (Conv2D) (None, 7, 7, 960) 153600 ['block_14_add[0][0]']
block_15_expand_BN (BatchN (None, 7, 7, 960) 3840 ['block_15_expand[0][0]']
ormalization)
block_15_expand_relu (ReLU (None, 7, 7, 960) 0 ['block_15_expand_BN[0][0]']
)
block_15_depthwise (Depthw (None, 7, 7, 960) 8640 ['block_15_expand_relu[0][0]']
iseConv2D)
block_15_depthwise_BN (Bat (None, 7, 7, 960) 3840 ['block_15_depthwise[0][0]']
chNormalization)
block_15_depthwise_relu (R (None, 7, 7, 960) 0 ['block_15_depthwise_BN[0][0]'
eLU) ]
block_15_project (Conv2D) (None, 7, 7, 160) 153600 ['block_15_depthwise_relu[0][0
]']
block_15_project_BN (Batch (None, 7, 7, 160) 640 ['block_15_project[0][0]']
Normalization)
block_15_add (Add) (None, 7, 7, 160) 0 ['block_14_add[0][0]',
'block_15_project_BN[0][0]']
block_16_expand (Conv2D) (None, 7, 7, 960) 153600 ['block_15_add[0][0]']
block_16_expand_BN (BatchN (None, 7, 7, 960) 3840 ['block_16_expand[0][0]']
ormalization)
block_16_expand_relu (ReLU (None, 7, 7, 960) 0 ['block_16_expand_BN[0][0]']
)
block_16_depthwise (Depthw (None, 7, 7, 960) 8640 ['block_16_expand_relu[0][0]']
iseConv2D)
block_16_depthwise_BN (Bat (None, 7, 7, 960) 3840 ['block_16_depthwise[0][0]']
chNormalization)
block_16_depthwise_relu (R (None, 7, 7, 960) 0 ['block_16_depthwise_BN[0][0]'
eLU) ]
block_16_project (Conv2D) (None, 7, 7, 320) 307200 ['block_16_depthwise_relu[0][0
]']
block_16_project_BN (Batch (None, 7, 7, 320) 1280 ['block_16_project[0][0]']
Normalization)
Conv_1 (Conv2D) (None, 7, 7, 1280) 409600 ['block_16_project_BN[0][0]']
Conv_1_bn (BatchNormalizat (None, 7, 7, 1280) 5120 ['Conv_1[0][0]']
ion)
out_relu (ReLU) (None, 7, 7, 1280) 0 ['Conv_1_bn[0][0]']
global_average_pooling2d_3 (None, 1280) 0 ['out_relu[0][0]']
(GlobalAveragePooling2D)
predictions (Dense) (None, 1000) 1281000 ['global_average_pooling2d_3[0
][0]']
==================================================================================================
Total params: 3538984 (13.50 MB)
Trainable params: 3504872 (13.37 MB)
Non-trainable params: 34112 (133.25 KB)
__________________________________________________________________________________________________
Load and Prepare the Image¶
In this section, the notebook handles the loading and preprocessing of the image that will be used for classification. It starts by retrieving the image from a GitHub repo, using the Python requests library to fetch the image data, which is then read into a PIL (Python Imaging Library) object. This image is resized to 224x224 pixels using the LANCZOS resampling method to match the input size requirements of the MobileNetV2 model. The image data is then converted into a numpy array, normalized by scaling the pixel values to the range [-1,1], and a batch dimension is added to prepare the image for model input. The shape of the preprocessed image confirms that it is correctly formatted as (1, 224, 224, 3), indicating one image of 224x224 pixels with three color channels.
The original image is shown below. It depicts a covered trailer on a highway.
# URL of the image
url = "https://raw.githubusercontent.com/matthewaaa123/CAP-6776-6640/main/image%20classification.jpeg"
# Fetch the image
response = requests.get(url)
image = Image.open(BytesIO(response.content))
# Display the image
plt.imshow(image)
plt.axis('off') # Hide axes
plt.show()
image = image.resize((224, 224), Image.LANCZOS)
# Preprocess the image
image = img_to_array(image)
image = np.expand_dims(image, axis=0)
image = preprocess_input(image)
np.shape(image)
(1, 224, 224, 3)
Finally, the image is displayed using Matplotlib, providing a visual confirmation of the preprocessing steps.
# Display the image
plt.imshow(image[0])
plt.axis('off') # Hide axes
plt.show()
This sequence ensures that the image is properly formatted and ready for classification by the neural network.
Image Classification¶
This section of the notebook demonstrates how image classification can be executed. Using the preprocessed image, the loaded MobileNetV2 model is used to predict the class of the image. The model.predict(image) function is called to process the image and generate predictions. These predictions are decoded using the np.argmax function, which extracts the index of the highest probability, indicating the model's most likely classification of the image. This step translates the model's numerical output into an interpretable result, providing insight into what the model perceives the image to represent. The classification process is quick, requiring only about one second to execute, showing the efficiency of using a pre-trained model like MobileNetV2 for real-time image analysis.
# Predict
predictions = model.predict(image)
# Decode the predictions
predicted_class = np.argmax(predictions, axis=-1)
print("Predicted Class", predicted_class)
1/1 [==============================] - 2s 2s/step Predicted Class [660]
The predicted class still needs to be decoded to understand the result.
Display the Results¶
After classifying the image, this section displays the results clearly. The model's predictions are decoded into understandable class labels with their corresponding confidence scores, using the decode_predictions function. This function fetches the top three predicted classes, providing a broader view of what the model perceives the image could represent. Each prediction is printed with its rank, label, and probability score, allowing for an easy interpretation of the model's output. For example, the highest probability is assigned to "mobile_home," followed by "trailer_truck" and "moving_van," reflecting varying degrees of confidence. This insight allows us to assess the model's accuracy and understand its decision-making process.
decoded_predictions = decode_predictions(predictions, top=3)[0] # Retrieve the top 3 most likely results
for i, (imagenet_id, label, score) in enumerate(decoded_predictions):
print(f"{i + 1}: {label} ({score:.2f})")
1: mobile_home (0.35) 2: trailer_truck (0.13) 3: moving_van (0.03)
Clearly, the image was correctly classified.
Conclusion¶
Overall, the image classifier was able to accurately classify the original image. The original picture captured a trailer being towed on a highway. The type of trailer is not completely clear, but it looks like it is a moving trailer or a small camper-type trailer, similar to the ones rented by U-Haul. The classifiers top three categories were mobile_home (0.35), trailer_truck (0.13), moving_van (0.03), which clearly accurately captures the images class. It can be described as a mobile-home type trailer, a trailer being towed, or a moving type of trailer, which is shown by classes. It is important to note that the granularity of these classes is based on the ImageNet dataset, and thus more specific/accurate classes may not exist in the dataset, so the image may best fit in these categories. MobileNetV2 was also very easy to use. It was very simple to download a pretrained version of the model, and using the included data preparation and prediction functions, it was easy to prepare the image and classify it. Forward propagation through the network was also very efficient, only requiring ~1s. Finally, the Keras library made it easy to decode the predictions of the model to understand the result.
References¶
This section contains the references that I used to create this notebook.